Comments (2)
You're right, once initialized the network is fixed to one exact resolution. We need image widths and heights that are multiples of 64, and so we have to setup upsampling and downsampling layers before/after the core network. The flow output even needs special treatment.
I can think of 4 different workflows here:
- (easiest, slowest) Call the docker script for each image pair individually.
- (still easy, a little faster) Change the Python script which the docker command executes. Currently the script initializes the network once, but it should not be too hard to rewrite it such that the network is reinitialized whenever the input size changes. This could be fast if your input list is sorted by image size, and if many input images share a common size (as should be the case in your example).
- (still easy, also faster) What you propose: Sort the inputs by sizes and create lists for each size class. If the whole docker overhead is not too bad, this might be as good as the previous option.
- (difficult, but fast) Actually rewrite the network layers such that they can deal with dynamic input sizes. I would ... not recommend this :P
from flownet2-docker.
Great! Thanks for your reply. I would try the 2nd method first.
The 4th would be too much work for me now :D
Big thanks again!
from flownet2-docker.
Related Issues (20)
- How long should a frame take to process? HOT 5
- libcudart.so.8.0: cannot open shared object file: No such file or directory HOT 15
- variable input sizes
- Will this work on latest version of CUDA 10? I am new please suggest me the changes in case it wonβt I am getting error docker:error response from daemon:oci runtime create failed when i the 2.1 HOT 2
- About the installation problem. HOT 2
- standard_init_linux.go:211: exec user process caused "exec format error" HOT 3
- How can I see result file HOT 8
- convert .flo file to .npy file HOT 2
- .flo file data HOT 2
- os.system error HOT 4
- CUDA driver version is insufficient for CUDA runtime version
- make error while building on docker. HOT 2
- about image quality HOT 2
- No output HOT 6
- No Outputs HOT 2
- Installation problem such as RPC failed and gnutls_handshake() failed HOT 1
- I can't see any output in the root folder HOT 1
- cuda error when feeding list of images HOT 2
- How to open .flow file? HOT 2
- How can I generate 2-channel optical flow image and save its x, y channel as .jpg image? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. πππ
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from flownet2-docker.